| VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer | | 53.7 | VPNeXt | 2025-02-23 |
| The Missing Point in Vision Transformers for Universal Image Segmentation | ✓ Link | 53.5 | ViT-P (InternImage-H) | 2025-05-26 |
| EVA: Exploring the Limits of Masked Visual Representation Learning at Scale | ✓ Link | 53.4 | EVA | 2022-11-14 |
| Representation Separation for Semantic Segmentation with Vision Transformers | | 52.6% | RSSeg-ViT-L (BEiT pretrain) | 2022-12-28 |
| Representation Separation for Semantic Segmentation with Vision Transformers | | 52.0% | RSSeg-ViT-L | 2022-12-28 |
| SegViT: Semantic Segmentation with Plain Vision Transformers | ✓ Link | 50.3% | SegViT (ours) | 2022-10-12 |
| Efficient Self-Ensemble for Semantic Segmentation | ✓ Link | 50.1% | SenFormer (Swin-L) | 2021-11-26 |
| Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation | ✓ Link | 45.4% | CAA (Efficientnet-B7) | 2021-01-19 |
| Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation | ✓ Link | 45.2% | HRNetV2 + OCR + RMI (PaddleClas pretrained) | 2019-09-24 |
| Scene Segmentation with Dual Relation-aware Attention Network | ✓ Link | 41.2% | DRAN(ResNet-101) | 2020-08-05 |
| Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation | ✓ Link | 41.2% | CAA (ResNet-101) | 2021-01-19 |
| Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation | ✓ Link | 40.5% | OCR (HRNetV2-W48) | 2019-09-24 |
| Expectation-Maximization Attention Networks for Semantic Segmentation | ✓ Link | 39.9% | EMANet | 2019-07-31 |
| Dual Attention Network for Scene Segmentation | ✓ Link | 39.7% | DANet (ResNet-101) | 2018-09-09 |
| Semantic Correlation Promoted Shape-Variant Context for Segmentation | ✓ Link | 39.6% | SVCNet (ResNet-101) | 2019-09-05 |
| Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation | ✓ Link | 39.5% | OCR (ResNet-101) | 2019-09-24 |
| Asymmetric Non-local Neural Networks for Semantic Segmentation | ✓ Link | 37.2% | Asymmetric ALNN | 2019-08-21 |
| Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation | ✓ Link | 35.7% | CCL (ResNet-101) | 2018-06-01 |
| RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation | ✓ Link | 33.6% | RefineNet (ResNet-101) | 2016-11-20 |
| DAG-Recurrent Neural Networks For Scene Labeling | | 31.2% | DAG-RNN (VGG-16) | 2015-09-02 |
| Fully Convolutional Networks for Semantic Segmentation | ✓ Link | 22.7% | FCN (VGG-16) | 2014-11-14 |